aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/kernels/CLReductionOperationKernel.cpp
AgeCommit message (Collapse)Author
2023-10-11Optimize CL reduction operationViet-Hoa Do
* Batch dimension is added to reduction operation. - All the dimensions higher than the batch dimension are collapsed so that the input and output tensors are always 3-4D. - CL kernel is called once instead of being repeatedly called to process each sliding window. Resolves: COMPMID-6443 Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com> Change-Id: Icd99939d52d3bb648f08537e5f52ef27e894061b Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10456 Reviewed-by: Jakub Sujak <jakub.sujak@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-09-28Apply clang-format on repositoryFelix Thomasmathibalan
Code is formatted as per a revised clang format configuration file(not part of this delivery). Version 14.0.6 is used. Exclusion List: - files with .cl extension - files that are not strictly C/C++ (e.g. Android.bp, Sconscript ...) And the following directories - compute_kernel_writer/validation/ - tests/ - include/ - src/core/NEON/kernels/convolution/ - src/core/NEON/kernels/arm_gemm/ - src/core/NEON/kernels/arm_conv/ - data/ There will be a follow up for formatting of .cl files and the files under tests/ and compute_kernel_writer/validation/. Signed-off-by: Felix Thomasmathibalan <felixjohnny.thomasmathibalan@arm.com> Change-Id: Ib7eb1fcf4e7537b9feaefcfc15098a804a3fde0a Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10391 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
2023-08-14Optimize CLReduce for Min/Max Axis=0Gunes Bayir
Resolves: COMPMID-6400 Change-Id: Id9935f9727f77a824afc75c35f044e3f5c173e0d Signed-off-by: Gunes Bayir <gunes.bayir@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10120 Benchmark: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2023-07-18Break up core/Utils.h to reduce unused code being included everywhereMatthew Bentham
Makes a small difference to compile times and opens up other opportunities to simplify code. Change-Id: I232876910bbe4fa9719f4a0ce4a54c090faeb5ef Signed-off-by: Matthew Bentham <Matthew.Bentham@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/532429 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9856 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com> Benchmark: Arm Jenkins <bsgcomp@arm.com>
2021-06-29Set up the framework to choose the default LWSGiorgio Arena
Resolve COMPMID-4486 Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Change-Id: Ib38b7943bd776a6d75d1da163908724c49eae73d Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5864 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-05-04Fix bug on CLReductionOperationGiorgio Arena
Execution window along the X axis needs to be collapsed on the 3rd axis (rather than the 2nd) since there could be implicit padding added along the Y Resolve COMPMID-4425 Change-Id: I9623a31749b737fea7c623cabdcfbf77cbe8f6dc Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5551 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: TeresaARM <teresa.charlinreyes@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-04-29Remove OpenCL padding: CLReductionOperationKernelGiorgio Arena
Change the parallel implementation across the X, now every thread computes one row Add missing test for MEAN_SUM Make reduction on any axis != 0 work with num_channels > 1 Resolve COMPMID-3917 Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Change-Id: Ib0f99540104e3c253bcd1ea637833db533f5e76e Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5522 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2021-03-29Remove usage of valid window region CL - NHWCMichalis Spyrou
Resolves: COMPMID-4153 Change-Id: Ib0d60c9acaac8aaf3946c62fc2d740b5ec6cee5c Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5301 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-12-14Enable FFT for FP16Giorgio Arena
Resolves: COMPMID-4051 Change-Id: I0c0bf97212dd281c19d5081e6247e7dc0c23cd6b Signed-off-by: Giorgio Arena <giorgio.arena@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4687 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-11-07COMPMID-3639: (3RDPARTY_UPDATE) Move CL kernels to srcSang-Hoon Park
Change-Id: I10d27db788e5086adae1841e3e2441cd9b76ef84 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4310 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-10-20COMPMID-3637: Move utility headers from arm_compute to srcSang-Hoon Park
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: If9d6fa8c900b68c4b6fd373f2fc1f9abb83ea917 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/4145 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-07-09COMPMID-3324: Adjusting capitalization of Arm copyright claim to reflect Arm ↵Michele Di Giorgio
preferred presentation Change-Id: Ib7dcfcbb24b408999dfae366b9da396485aacf78 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3525 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-22COMPMID-3280: Make all ML primitives for CL use the new interface - Part1 - Fix3Manuel Bottini
- const fix in the CLKernels part 3 Change-Id: I9cfb896f334145249a97c9287fa00399b8319a8e Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3075 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2020-04-17COMPMID-3280: Make all ML primitives for CL use the new interface - Part 1Manuel Bottini
- Only CLKernels have been updated Change-Id: Ife55b847c2e39e712a186eb6ca452503d5b66937 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3001 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-03-10COMPMID-3069: Improve build time by splitting up ToolchainSupport.hMatthew Bentham
Split out the parts of ToolchainSupport coming from <memory> and the parts coming from <string> into their own new header files. This accounts for 99% of uses of ToolchainSupport, which means that expensive header files such as arm_neon.h don't need to be included everywhere. Knocks about 10% of compilation time off kernel files. Signed-off-by: Matthew Bentham <matthew.bentham@arm.com> Change-Id: I2ae718fe766b5ff28608812b0f686f30eeac1b21 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2852 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-02-27COMPMID-3223: Fix -14 error code on Firefly for CLReductionMichele Di Giorgio
Wrong data type was used for MIN/MAX reduction causing segfaults. This patch also simplifies window calculation for non-parallel reduction. Change-Id: I0abd9e84540801f92b306accd1439ff5df126a9e Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2792 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2020-02-07COMPMID-2838: Add support for QASYMM8 production reduce operation to CLMichalis Spyrou
Change-Id: I3e642ea0bffca038a697b8cfb5db38e337876edc Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2703 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2020-02-07COMPMID-2762: Add support for QASYMM8_SIGNED in CLReductionOperation and ↵Michalis Spyrou
CLReduceMean Change-Id: Ib6babd9ad80c57cf21c2f0ee2aab404221088595 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2670 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
2019-12-03COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAXManuel Bottini
Introducing new CLArgMinMax kernel Change-Id: I0b8254207cc3859d19ceef9b6429cf5c1c586db0 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/2202 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
2019-11-12COMPMID-2671 use Signed32 for default output data type of ArgMinMaxSang-Hoon Park
Signed32 is used as data types before and after reshaping of ArgMinMax. Change-Id: I230af43a931d4e106de6c72f716ced1dab511084 Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/2262 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
2019-10-30COMPMID-2707: add keep_dims parameter to Reduction OperationSang-Hoon Park
The added parameter is used to decide whether or not to keep the target dimension of reduction operation. ArgMinMax operations will always remove the reduced dimension. Following things are updated to support the parameter. - [CL/NEON] functions and reference kernel - [CL/NEON] ArgMinMax function to use ReductionOperation function - [CL/NEON] validation test suite for Reduction and ArgMinMax operations to validate the added parameter - ReductionOperationFixture is modified NOT to pre-populate output tensor and now relies on underlying kernel/function. - Adjust CL validation test suite for Reduction operation to remove excessive test cases with axis values beyond input tensor's dimension. Change-Id: I3e24d276ed469a4201f323001708f0c525f11c4f Signed-off-by: Sang-Hoon Park <sang-hoon.park@arm.com> Reviewed-on: https://review.mlplatform.org/c/2167 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-10-18Revert "COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAX"Manuel Bottini
This reverts commit 36debd4472839997fd3b6ec9d58530d95e3c17de. Change-Id: I45d63a63cebfd4582214b488027c2b14f492fdc1 Reviewed-on: https://review.mlplatform.org/c/2120 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-10-04COMPMID-1816: Use parallel reduction on 0 axis in CL ARG_MIN/ARG_MAXManuel Bottini
Parallelization of reduction along x axes Removal of the use of padding Fast vector implementation of reduction operation Change-Id: I3a56c57b9fc1135cf8f79d1021d966ea22b084b1 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/1791 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-09-30COMPMID-2671: Change ArgMinMax NEON/CL output type to Signed32Michele Di Giorgio
Change-Id: I718f3884928271c5b0afb259d5bfe9df284f18e6 Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-on: https://review.mlplatform.org/c/1995 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-08-24COMPMID-2451: Use kernel lws_hint() on enqueueGeorgios Pinitas
Avoid querying device's default lws on kernel enqueue as this is already cached in the kernel during configuration. Change-Id: Ia26ecb712caeb8f042356815e0cfd23522764d27 Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/1803 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-05-24COMPMID-2278: Implement REDUCE_MAX operator for CL.Usama Arif
Change-Id: Ie23e3ddc45d6f5506a63f935758a215ba7412bf5 Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/186031 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: bsgcomp <bsgcomp@arm.com> Reviewed-on: https://review.mlplatform.org/c/1214 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
2019-05-22COMPMID-2281: Implement REDUCE_MIN operator for CLUsama Arif
Change-Id: I60fd3affad0ab5a2f1cef18aaa46dc2dc448caeb Signed-off-by: Usama Arif <usama.arif@arm.com> Reviewed-on: https://review.mlplatform.org/c/1194 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Marquez <pablo.tello@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-05-20COMPMID-2243 ArgMinMaxLayer: support new datatypesMichalis Spyrou
Change-Id: I846e833e0c94090cbbdcd6aee6061cea8295f4f9 Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com> Reviewed-on: https://review.mlplatform.org/c/1131 Reviewed-by: Giuseppe Rossini <giuseppe.rossini@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-04-11COMPMID-1959: Implements 2D FFT on OpenCLGeorgios Pinitas
Change-Id: I73cf3984a5463acc854c8a59dc2bd9a5234cd99c Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/c/936 Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-03-29COMPMID-1995: Removed layout checks from Reduction opsPablo Tello
Change-Id: Icd8d153da63c53c51d3a2e3ea6bc7de5938934f2 Signed-off-by: Pablo Tello <pablo.tello@arm.com> Reviewed-on: https://review.mlplatform.org/c/913 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2019-02-22COMPMID-1710: Add FP16 support checks.Georgios Pinitas
Change-Id: I6291847935996859ab245160714f9fbefb03b5be Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Reviewed-on: https://review.mlplatform.org/761 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2019-02-15COMPMID-1710: Add check on different input/output quantization info were not ↵Isabella Gottardi
supported Change-Id: Id64dab5e2de341316238506d4fb3ab82b992753d Signed-off-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-on: https://review.mlplatform.org/697 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2019-01-14COMPMID-1724: CL Implement ProdManuel Bottini
Change-Id: I17e51f25064b53a8f7e13d6fcbecc14a192de103 Reviewed-on: https://review.mlplatform.org/387 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-12-07COMPMID-1821 (Nighlty) CL/ArgMinMax/Float/ clEnqueueMapBuffer failuresMichalis Spyrou
Change-Id: I5a9d698f459fd7efdbe85d70d092e79e961cb4dd Reviewed-on: https://review.mlplatform.org/368 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
2018-11-30COMPMID-1728 CL: Implement ArgMax/ArgMinMichalis Spyrou
Change-Id: I7eae2e55cc0b0b7bbebb7617299daaca6f75f40c Reviewed-on: https://review.mlplatform.org/292 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-1632 Add CLL2NormalizationLayer for NHWC and FP32Michalis Spyrou
Change-Id: Iae22554d5fe893fd22a000eab5bfd8275ea06eb3 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/154102 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: bsgcomp <bsgcomp@arm.com>
2018-11-02COMPMID-1574 Implement ReduceMean in OpenCLMichalis Spyrou
Change-Id: Id331199f569f52a37280a9ada5bf84694580b93c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/152843 Tested-by: bsgcomp <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
2018-11-02COMPMID-1478: Stop relying on static default OpenCL objects in cl2.hppAnthony Barbier
This causes problems when ACL is used as a shared library on Android. Fixes some problems related to creation / destruction order between the Graph's CL backend and core / runtime Change-Id: I716d63fd42f4586df1ffbb6fa97e4db06d3a781b Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143228 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-1410 (Nightly) Mismatches in CLMeanStd function for floatMichalis Spyrou
Change CLReductionOperation border to be multiple of 64 instead of 16. The opencl kernel works only with local_size(0) being a power of 2. This will generate a padding of 63 if input_width % 64 = 1, but I don't think it's a big issue and it keeps the border calculation pretty simple. Also, increased tolerance for fp32 because there were mismatches for the 4K image. Change-Id: Id44990a262b2d6eff4c8ce56eb7c886274d9847e Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/143415 Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Jenkins <bsgcomp@arm.com>
2018-11-02COMPMID-1226 Extend CLMeanStdDev to support FP32 / FP16Michalis Spyrou
- Extend support for FP16 in CLReduction. - For F16/F32 MeanStdDev we perform one reduction operation for mean and one for stddev and we calculate the final result in the host CPU. Change-Id: Iad2099f26c0ba7969737d22f00c6c275634d875c Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/135870 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-970 : Remove QS8 / QS16 supportVidhya Sudhan Loganathan
Removed fixed point related code. Change-Id: I487acf138dace3b0450e0d72ca7071eaec254566 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/137678 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-1143 - Excessive padding in CLReductionOperationKernel when ↵Michalis Spyrou
configuring window Now max padding is equal to 15 instead of 127. If input width is less than 128 we decrease the number of threads in the WG. Change-Id: I5ff0b6fd8cb46143ba49e745ec9ad01f691bdd80 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/134152 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
2018-11-02COMPMID-948: Remove unused code in CLReductionOperationKernelJohn Richardson
Remove redudant code left over from validation method refactoring. Update output shapes in CL/ReductionOperation Validate test suite. Change-Id: Ica846dd7f65380fa21708472e10b5bc609a32027 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/131207 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Pablo Tello <pablo.tello@arm.com> Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-948: Add validation to CLL2NormalizeLayerJohn Richardson
Change-Id: I452a718a60b81da51cd3e98641fd99c86c4debab Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129451 Tested-by: Jenkins <bsgcomp@arm.com> Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
2018-11-02COMPMID-834 Fix arm_compute_nightly_validation getting killedMichalis Spyrou
Changed CLReductionOperationKernel: Now each kernel computes a 2D slice instead of 1D. This reduces the memory footprint from around 1.6Gb for a 4k input image to a few Mb, which was caused by the __local memory and was probably the cause for this bug. Change-Id: I71ac71ff09b041c945a134177600f0f3475e48cf Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/117835 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Anthony Barbier <anthony.barbier@arm.com>
2018-11-02COMPMID-417 Fix reduction kernel's __local buffer sizeMichalis Spyrou
Change-Id: If97a79d86b174b1d9b41360303d624e3b2d22001 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/87703 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
2018-11-02COMPMID-476 L2 Normalization for CLMichalis Spyrou
Change-Id: I88f87173645880eb823916c5d4ac884c372a4fb4 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/83269 Reviewed-by: Anthony Barbier <anthony.barbier@arm.com> Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
generated by cgit v1.2.1 (git 2.23.0) at 2024-05-16 03:35:49 +0000